相关论文: LoMix: Learnable Weighted Multi-Scale Logits Mixin…

We present a next-generation neural network architecture, MOSAIC, for efficient and accurate semantic image segmentation on mobile devices. MOSAIC is designed using commonly supported neural operations by diverse mobile hardware platforms…

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…

This study aimed to enhance disease classification accuracy from retinal fundus images by integrating fine-grained image features and global textual context using a novel multimodal deep learning architecture. Existing multimodal large…

In this study, the performance of existing U-shaped neural network architectures was enhanced for medical image segmentation by adding Transformer. Although Transformer architectures are powerful at extracting global information, its…

We present {\mu}Split, a dedicated approach for trained image decomposition in the context of fluorescence microscopy images. We find that best results using regular deep architectures are achieved when large image patches are used during…

Multimodal deep learning methods capture synergistic features from multiple modalities and have the potential to improve accuracy for stress detection compared to unimodal methods. However, this accuracy gain typically comes from high…

Universal medical image segmentation models have emerged as a promising paradigm due to their strong generalizability across diverse tasks, showing great potential for a wide range of clinical applications. This potential has been partly…

In recent literature there are plenty of works that combine handcrafted and learnable regularizers to solve inverse imaging problems. While this hybrid approach has demonstrated promising results, the motivation for combining handcrafted…

Given the special situation of modeling gigapixel images, multiple instance learning (MIL) has become one of the most important frameworks for Whole Slide Image (WSI) classification. In current practice, most MIL networks often face two…

Multimodal semantic communication has great potential to enhance downstream task performance by integrating complementary information across modalities. This paper introduces ProMSC-MIS, a novel Prompt-based Multimodal Semantic…

Multimodal clinical prediction faces three challenges: multiple foundation models (FMs) with complementary strengths per modality, pervasive missing modalities at training and test time, and sample-specific variation in modality…

Selecting the best data mixture is critical for successful Supervised Fine-Tuning (SFT) of Multimodal Large Language Models. However, determining the optimal mixture weights across multiple domain-specific datasets remains a significant…

Large vision-language models (LVLMs) achieve impressive performance, yet their internal decision-making processes remain opaque, making it difficult to determine if the success stems from true multimodal fusion or from reliance on unimodal…

Many studies have revealed that large language models (LLMs) exhibit uneven awareness of different contextual positions. Their limited context awareness can lead to overlooking critical information and subsequent task failures. While…

Vision-Language Models (VLMs) have achieved substantial progress across a wide range of understanding and reasoning tasks, driven by large-scale image-text training aimed at multimodal fusion. Ideally, replacing a textual question with its…

Whole slide images (WSIs) in computational pathology (CPath) pose a major computational challenge due to their gigapixel scale, often requiring the processing of tens to hundreds of thousands of high-resolution patches per slide. This…

While critical for the practical progress of spectrum sharing, modulation recognition has so far been investigated under unrealistic assumptions: (i) a transmitter's bandwidth must be scanned alone and in full, (ii) prior knowledge of the…

Deep learning based disease detection and segmentation algorithms promise to improve many clinical processes. However, such algorithms require vast amounts of annotated training data, which are typically not available in the medical context…

Latent diffusion models (LDMs) enable high-fidelity synthesis by operating in learned latent spaces. However, training state-of-the-art LDMs requires complex staging: a tokenizer must be trained first, before the diffusion model can be…

Map-free LiDAR localization systems accurately localize within known environments by predicting sensor position and orientation directly from raw point clouds, eliminating the need for large maps and descriptors. However, their long…